Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6280 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3543. Min Range: -6.3543
Max Act: 6.3543. Min Act: -0.1700
Data Index: 2018588 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3543. Min Range: -6.3543
Max Act: 6.1355. Min Act: -0.1700
Data Index: 2311256 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3543. Min Range: -6.3543
Max Act: 6.0418. Min Act: -0.1700
Data Index: 5874682 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3543. Min Range: -6.3543
Max Act: 6.0105. Min Act: -0.1700
Data Index: 8779354 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3543. Min Range: -6.3543
Max Act: 6.0105. Min Act: -0.1700
Data Index: 7611649 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.9793. Min Act: -0.1700
Data Index: 2702417 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.9793. Min Act: -0.1700
Data Index: 4308742 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.9168. Min Act: -0.1700
Data Index: 8597385 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.9480. Min Act: -0.1700
Data Index: 6936393 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.9480. Min Act: -0.1700
Data Index: 7862312 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.8855. Min Act: -0.1700
Data Index: 7271414 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.9168. Min Act: -0.1700
Data Index: 103747 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.9168. Min Act: -0.1700
Data Index: 6947992 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.9168. Min Act: -0.1700
Data Index: 1183511 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.9168. Min Act: -0.1700
Data Index: 5452389 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.8855. Min Act: -0.1700
Data Index: 4378110 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.8855. Min Act: -0.1700
Data Index: 448157 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.8855. Min Act: -0.1700
Data Index: 6095054 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.8855. Min Act: -0.1700
Data Index: 3950917 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3543. Min Range: -6.3543
Max Act: 5.8855. Min Act: -0.1700
Data Index: 2477415 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19